Sciweavers

135 search results - page 19 / 27
» Improving Multi-Step Prediction of Learned Time Series Model...
Sort
View
ICML
2007
IEEE
14 years 8 months ago
Three new graphical models for statistical language modelling
The supremacy of n-gram models in statistical language modelling has recently been challenged by parametric models that use distributed representations to counteract the difficult...
Andriy Mnih, Geoffrey E. Hinton
SIGGRAPH
1999
ACM
13 years 11 months ago
Voice Puppetry
We introduce a method for predicting a control signal from another related signal, and apply it to voice puppetry: Generating full facial animation from expressive information in ...
Matthew Brand
BMCBI
2006
239views more  BMCBI 2006»
13 years 7 months ago
Applying dynamic Bayesian networks to perturbed gene expression data
Background: A central goal of molecular biology is to understand the regulatory mechanisms of gene transcription and protein synthesis. Because of their solid basis in statistics,...
Norbert Dojer, Anna Gambin, Andrzej Mizera, Bartek...
ICML
2009
IEEE
14 years 8 months ago
Factored conditional restricted Boltzmann Machines for modeling motion style
The Conditional Restricted Boltzmann Machine (CRBM) is a recently proposed model for time series that has a rich, distributed hidden state and permits simple, exact inference. We ...
Graham W. Taylor, Geoffrey E. Hinton
AAAI
2007
13 years 9 months ago
Predictive Exploration for Autonomous Science
Often remote investigations use autonomous agents to observe an environment on behalf of absent scientists. Predictive exploration improves these systems’ efficiency with onboa...
David R. Thompson